Chat model by kakaocorp · 30.67B parameters
Everything this chip runs, machine by machine: MacBook Pro 14" M5 Pro, MacBook Pro 16" M5 Pro
kanana 2 30b a3b instruct 2601 can run but will be tight at 85% of RAM. Consider a lower quantization or closing other apps.
— tok/s
Q4_K_M · 20.3 GB · Benchmark needed
Alternative: Q3_K_M (17.2 GB, ~144 tok/s)
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 34.7 GB | ~66 tok/s | ✗ |
| Q6_K | 27.0 GB | ~86 tok/s | ✗ |
| Q5_K_M | 23.4 GB | ~102 tok/s | ✗ |
| Q4_K_M Recommended | 20.3 GB | ~119 tok/s | ✓ |
| Q3_K_M | 17.2 GB | ~144 tok/s | ✓ |
| Q2_K | 13.9 GB | ~187 tok/s | ✓ |
Closest matches by use case and parameter count.
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free